A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[docs] fix nixl kv_connector_extra_config.backends key (#25565)
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io> Signed-off-by: Peter Pan <peter.pan@daocloud.io> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Peter Pan committed
Sep 24, 2025 at 19:00 UTC
b1068903fdca26cf6b4a1a51a32c3365ce3ac636
2 files changed
+2
-2
docs/features/disagg_prefill.md
+1
-1
@@ -34,7 +34,7 @@ Now supports 5 types of connectors:
34
For NixlConnector, you may also specify one or multiple NIXL_Backend. Such as:
35
36
```bash
37
- --kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both", "kv_buffer_device":"cuda", "kv_connector_extra_config":{"backend":["UCX", "GDS"]}'
37
+ --kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both", "kv_buffer_device":"cuda", "kv_connector_extra_config":{"backends":["UCX", "GDS"]}}'
38
```
39
40
- **OffloadingConnector**: enable offloading of KV data to CPU memory, customizing the CPU block size (in tokens) and number of blocks to allocate (per worker):
docs/serving/expert_parallel_deployment.md
+1
-1
@@ -193,7 +193,7 @@ For production deployments requiring strict SLA guarantees for time-to-first-tok
193
194
1. **Install gdrcopy/ucx/nixl**: For maximum performance, run the [install_gdrcopy.sh](gh-file:tools/install_gdrcopy.sh) script to install `gdrcopy` (e.g., `install_gdrcopy.sh "${GDRCOPY_OS_VERSION}" "12.8" "x64"`). You can find available OS versions [here](https://developer.download.nvidia.com/compute/redist/gdrcopy/CUDA%2012.8/). If `gdrcopy` is not installed, things will still work with a plain `pip install nixl`, just with lower performance. `nixl` and `ucx` are installed as dependencies via pip.
195
196
-2. **Configure Both Instances**: Add this flag to both prefill and decode instances `--kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both"}`. Noted, you may also specify one or multiple NIXL_Backend. Such as: `--kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both", "kv_connector_extra_config":{"backend":["UCX", "GDS"]}'`
196
+2. **Configure Both Instances**: Add this flag to both prefill and decode instances `--kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both"}`. Noted, you may also specify one or multiple NIXL_Backend. Such as: `--kv-transfer-config '{"kv_connector":"NixlConnector","kv_role":"kv_both", "kv_connector_extra_config":{"backends":["UCX", "GDS"]}}'`
197
198
3. **Client Orchestration**: Use the client-side script below to coordinate prefill/decode operations. We are actively working on routing solutions.
199